[HTML][HTML] A comprehensive survey of image augmentation techniques for deep learning

M Xu, S Yoon, A Fuentes, DS Park - Pattern Recognition, 2023 - Elsevier
Although deep learning has achieved satisfactory performance in computer vision, a large
volume of images is required. However, collecting images is often expensive and …

Efficient deep learning: A survey on making deep learning models smaller, faster, and better

G Menghani - ACM Computing Surveys, 2023 - dl.acm.org
Deep learning has revolutionized the fields of computer vision, natural language
understanding, speech recognition, information retrieval, and more. However, with the …

Machine learning algorithms in civil structural health monitoring: A systematic review

M Flah, I Nunez, W Ben Chaabene… - Archives of computational …, 2021 - Springer
Abstract Applications of Machine Learning (ML) algorithms in Structural Health Monitoring
(SHM) have become of great interest in recent years owing to their superior ability to detect …

Parallel learning: Overview and perspective for computational learning across Syn2Real and Sim2Real

Q Miao, Y Lv, M Huang, X Wang… - IEEE/CAA Journal of …, 2023 - ieeexplore.ieee.org
The virtual-to-real paradigm, ie, training models on virtual data and then applying them to
solve real-world problems, has attracted more and more attention from various domains by …

On translation invariance in cnns: Convolutional layers can exploit absolute spatial location

OS Kayhan, JC Gemert - … of the IEEE/CVF Conference on …, 2020 - openaccess.thecvf.com
In this paper we challenge the common assumption that convolutional layers in modern
CNNs are translation invariant. We show that CNNs can and will exploit the absolute spatial …

A multi-stage semi-supervised learning approach for intelligent fault diagnosis of rolling bearing using data augmentation and metric learning

K Yu, TR Lin, H Ma, X Li, X Li - Mechanical Systems and Signal Processing, 2021 - Elsevier
Limited condition monitoring data are recorded with label information in practice, which
make the fault identification task more challenging. A semi-supervised learning (SSL) …

An efficient multi-scale CNN model with intrinsic feature integration for motor imagery EEG subject classification in brain-machine interfaces

AM Roy - Biomedical Signal Processing and Control, 2022 - Elsevier
Objective Electroencephalogram (EEG) based motor imagery (MI) classification is an
important aspect in brain-machine interfaces (BMIs) which bridges between neural system …

Regularization for deep learning: A taxonomy

J Kukačka, V Golkov, D Cremers - arxiv preprint arxiv:1710.10686, 2017 - arxiv.org
Regularization is one of the crucial ingredients of deep learning, yet the term regularization
has various definitions, and regularization methods are often studied separately from each …

Knowledge distillation improves graph structure augmentation for graph neural networks

L Wu, H Lin, Y Huang, SZ Li - Advances in Neural …, 2022 - proceedings.neurips.cc
Graph (structure) augmentation aims to perturb the graph structure through heuristic or
probabilistic rules, enabling the nodes to capture richer contextual information and thus …

Failures of Photovoltaic modules and their Detection: A Review

MW Akram, G Li, Y **, X Chen - Applied Energy, 2022 - Elsevier
Photovoltaic (PV) has emerged as a promising and phenomenal renewable energy
technology in the recent past and the PV market has developed at an exponential rate …